Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 909
    Prev
    Next
    INDEX
    Explanations

    mentions of a "slot," such as a position in a sports team or a technical slot in a machine

    oai_token-act-pair · gpt-3.5-turbo

    references to "slot" regarding a specific context, such as sports positions or device connectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.66
    omorphic
    -0.66
    vironment
    -0.66
    omen
    -0.65
    issance
    -0.62
    harm
    -0.61
    externalActionCode
    -0.58
    otype
    -0.57
     Principles
    -0.56
    é»Ĵ
    -0.56
    POSITIVE LOGITS
    tery
    1.07
    ting
    1.00
     slots
    0.95
    Slot
    0.92
     slot
    0.91
    ular
    0.91
    ioned
    0.87
    ularity
    0.85
    busters
    0.78
    holders
    0.77
    Activations Density 0.011%

    No Known Activations